© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94180
    Prev
    Next
    INDEX
    Explanations

    the + organization name

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on tokens that are part of formal named entities—titles, organization or society names, conferences/meetings, and award bodies (including their numeric or date components).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dimensioni
    -0.86
     danken
    -0.85
     Mitglied
    -0.83
     *"
    -0.83
     teléfonos
    -0.80
    ')],
    -0.80
     แล้ว
    -0.79
    setOn
    -0.79
    ובר
    -0.79
    unking
    -0.79
    POSITIVE LOGITS
     American
    2.22
    American
    1.67
     National
    1.62
     International
    1.45
     american
    1.35
     Americans
    1.27
    National
    1.23
     американ
    1.22
    american
    1.19
     European
    1.18
    Activations Density 0.049%

    No Known Activations